Model Releases
Teaching Language Models How to Code Like Learners: Conversational Serialization for Student Simulation
arXiv:2604.10720v1 Announce Type: new Abstract: Artificial models that simulate how learners act and respond within educational systems are a promising tool for evaluating tutoring strategies and feed
arXiv:2604.10720v1 Announce Type: new Abstract: Artificial models that simulate how learners act and respond within educational systems are a promising tool for evaluating tutoring strategies and feedback mechanisms at scale. However, many existing approaches in programming education rely on prompting large, proprietary language models, raising concerns around privacy, cost, and dependence. In this work, we propose a method for training open-weight artificial programming learners using authentic student process data. Our approach serializes temporal log traces into a conversational format, representing each student's problem-solving process as a dialogue between the learner and their automated assessment system. Student code submissions and environment feedback, such as test outcomes, grades, and error traces, form alternating conversational turns, enabling models to learn from the iterative debugging process. We additionally introduce a training pipeline combining supervised fine-tuning with preference optimization to align models with authentic student debugging behavior. We evaluate our framework by training Qwen models at 4B and 8B scales on a large-scale dataset of real student submissions to Python programming assignments. Our results show that incorporating environment feedback strengthens the models' ability to replicate student debugging behavior, improving over both prior code-only approaches and prompted large language models baselines in functional alignment and code similarity. We release our code to support reproducibility.
Related
- Facial-Expression-Aware Prompting for Empathetic LLM Tutoring
- Assessing the Pedagogical Readiness of Large Language Models as AI Tutors in Low-Resource Contexts: A Case Study of Nepal's K-10 Curriculum
- Restoring Heterogeneity in LLM-based Social Simulation: An Audience Segmentation Approach
- Evaluating Answer Leakage Robustness of LLM Tutors against Adversarial Student Attacks
Source: arXiv cs.AI | 2026-04-14